writeup: faustctf 2018: jodlgang - sigflag1. application overview uwsgi: web server gateway...

Writeup: FaustCTF 2018: Jodlgang

Student: Markus VoglTeam: SIGFLAG.atUni: JKU LinzInstitute: Institute for Network and SecuritySponsor:VACE

Overview

01 Application Overview02 Problem analysis03 Machine Learning: VGG1604 The stupid solution05 The smart solution

1. Application Overview

1. Application Overview

● UWSGI: Web Server Gateway Interface● Django Webapp on port 8000

● Bootstrap CSS + JS + html templates● Virtual python env + separate user

● No easy cross service attacks● SQLite DB● Tensorwow

● Numpy implementation of Tensorflow● 500MB .h5 pretrained model

1. Application Overview: Database

2. Problem analysis: backends.py

2. Problem analysis

● Login with one of of 530 known emails● “Password” is an image

– Must be (cnn.input_width * cnn.input_width * 3)– So: 224 x 224 x 3 = square RGB

● Cnn.inference(face)– Argmax– must be >0.5

2. Problem Analysis: Model

2. Problem Analysis: Model #2

Wait a second….

3. Machine Learning: VGG

3. Machine Learning: Softmax

3. ML – The softmax issue

● Does this mean….File: potato.jpg User: Helena Döring Prob: 0.63

File: bitconnect_dude.jpg User: Marlene Schuster Prob: 0.51

File: trump.jpg User: Paula Hahn Prob: 0.99

File: bitcoin.jpg User: Pia Ingerfurth Prob: 0.35

3. Machine Learning: CelebA Dataset

● Right: User: Theo-Fuchs.jpg fromnetwork traffic (user 60)

● Bottom: CelebA– 200k images– 10k identities– 178 × 218 px

4. The stupid solution

1.Take random CelebA image

2.Feed it to pretrained model

3.Get classifications → Same for every team

4.If max(classifications) > 50% → JACKPOT

5.Save as id = argmax(classifications)

6.Repeat on many computers, merge images

7.Try every image-ID on every team, because you forget Theo is #60 and you are team #60Now they dump your traffic and reuse your images

4. The stupid solution: Code

5. The smart solution

● Import weights into Keras/Tensorflow like a sane person → get x100 speedup on GPU

● Use a pretrained optimizer to maximize the class of a given output: “Activation maximization”

● Get trippy images like this.● Read “How convolutional

neural nets see the world”to understand why